1
Your word
measured
“They hired two new secretaries in the department”
Definitions come from WordNet, a hand-curated dictionary.
engage or hire for work
contratar is Spanish for hiring, and every measurement below was made on that English word. Definitions come from English WordNet; Open Multilingual WordNet supplies the Spanish headword, not a Spanish definition.
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“They hired two new secretaries in the department”
Definitions come from WordNet, a hand-curated dictionary.
This panel splits contratar itself, not hiring — a tokenizer does not care what language it is fed. It is the only panel here that does.
This is the tokenizer splitting text, not the model understanding it.
Shade shows how close the model puts each word to hiring, 1 of 8 also appear in the dictionary.
fire is the dictionary opposite of hiring, yet this model puts it closer than 1 of the 7 synonyms it can score. Opposites share the sentences a word lives in, so cosine alone cannot tell them apart - which is why the dictionary seeds this list rather than the geometry.
Shade shows how close the model puts each word to hiring, 1 of 8 also appear in the dictionary.
fire is the dictionary opposite of hiring, yet this model puts it closer than 2 of the 7 synonyms it can score. Opposites share the sentences a word lives in, so cosine alone cannot tell them apart - which is why the dictionary seeds this list rather than the geometry.
Shade shows how close the model puts each word to hiring, 1 of 8 also appear in the dictionary.
Model neighbours are distributional, not dictionary synonyms. Two words can be close because they appear in similar sentences, which is why an antonym can outscore a synonym here.
Scores are projections onto axes we defined from anchor words, not labels the model assigns.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to hiring. That gap is the model’s own learned association.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to hiring. That gap is the model’s own learned association.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to hiring. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.